Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax elements and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX math symbols and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.94
     المعيارى
    -0.84
    StoryboardSegue
    -0.82
     deſſen
    -0.80
     Administrativna
    -0.79
     otomatig
    -0.79
    httphttps
    -0.76
    ஦
    -0.75
     Weiſe
    -0.75
    Билгалдахарш
    -0.75
    POSITIVE LOGITS
     general
    0.33
     interior
    0.30
     normal
    0.29
     ordinary
    0.29
     less
    0.27
     Pl
    0.26
     others
    0.26
     depending
    0.26
     —
    0.26
    ]));
    0.26
    Act Density 0.102%

    No Known Activations